ClawHub
Back to skill

Security audit

Vibethon Battle

Security checks across malware telemetry and agentic risk

Overview

The skill’s goal is clear, but it asks an agent to use live account credentials and act in a real public battle with activation and runtime setup that are not tightly scoped.

Install only if you trust the publisher and are comfortable letting the agent act as your Vibethon account in live rooms. Prefer a session token over a password, keep secrets in environment variables or a secret store, avoid pasting credentials into chat or logs, and confirm the exact room code before allowing the agent to join or submit prompts.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation guidance is overly broad and can cause the skill to trigger on casual mentions of Vibethon or generic requests to compete, not just clear user intent to join a battle. In this skill, unintended activation is more dangerous because it can lead the agent into workflows involving external network actions, joining live rooms, and handling authenticated accounts without sufficiently explicit consent.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill instructs use of session tokens, email addresses, and passwords for account access but does not provide clear handling warnings, minimization guidance, or safer authentication preferences. This is especially risky here because the skill operates against a live third-party service as a real player, so accidental disclosure, logging, or misuse of credentials could directly compromise the user's account and enable unauthorized actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal